def evaluation_meansquarederror_modular (ground_truth, predicted): from modshogun import RegressionLabels from modshogun import MeanSquaredError ground_truth_labels = RegressionLabels(ground_truth) predicted_labels = RegressionLabels(predicted) evaluator = MeanSquaredError() mse = evaluator.evaluate(predicted_labels,ground_truth_labels) return mse
def evaluation_cross_validation_regression(train_fname=traindat,
label_fname=label_traindat,
width=0.8,
tau=1e-6):
from modshogun import CrossValidation, CrossValidationResult
from modshogun import MeanSquaredError, CrossValidationSplitting
from modshogun import RegressionLabels, RealFeatures
from modshogun import GaussianKernel, KernelRidgeRegression, CSVFile
# training data
features = RealFeatures(CSVFile(train_fname))
labels = RegressionLabels(CSVFile(label_fname))
# kernel and predictor
kernel = GaussianKernel()
predictor = KernelRidgeRegression(tau, kernel, labels)
# splitting strategy for 5 fold cross-validation (for classification its better
# to use "StratifiedCrossValidation", but here, the std x-val is used
splitting_strategy = CrossValidationSplitting(labels, 5)
# evaluation method
evaluation_criterium = MeanSquaredError()
# cross-validation instance
cross_validation = CrossValidation(predictor, features, labels,
splitting_strategy,
evaluation_criterium)
# (optional) repeat x-val 10 times
cross_validation.set_num_runs(10)
# (optional) request 95% confidence intervals for results (not actually needed
# for this toy example)
cross_validation.set_conf_int_alpha(0.05)
# (optional) tell machine to precompute kernel matrix. speeds up. may not work
predictor.data_lock(labels, features)
# perform cross-validation and print(results)
result = cross_validation.evaluate()
def modelselection_grid_search_krr_modular (fm_train=traindat,fm_test=testdat,label_train=label_traindat,\
width=2.1,C=1,epsilon=1e-5,tube_epsilon=1e-2):
from modshogun import CrossValidation, CrossValidationResult
from modshogun import MeanSquaredError
from modshogun import CrossValidationSplitting
from modshogun import RegressionLabels
from modshogun import RealFeatures
from modshogun import KernelRidgeRegression
from modshogun import GridSearchModelSelection
from modshogun import ModelSelectionParameters
# training data
features_train = RealFeatures(traindat)
features_test = RealFeatures(testdat)
labels = RegressionLabels(label_traindat)
# labels
labels = RegressionLabels(label_train)
# predictor, set tau=0 here, doesnt matter
predictor = KernelRidgeRegression()
# splitting strategy for 5 fold cross-validation (for classification its better
# to use "StratifiedCrossValidation", but the standard
# "StratifiedCrossValidationSplitting" is also available
splitting_strategy = CrossValidationSplitting(labels, 5)
# evaluation method
evaluation_criterium = MeanSquaredError()
# cross-validation instance
cross_validation = CrossValidation(predictor, features_train, labels,
splitting_strategy,
evaluation_criterium)
# (optional) repeat x-val (set larger to get better estimates)
cross_validation.set_num_runs(2)
# print all parameter available for modelselection
# Dont worry if yours is not included but, write to the mailing list
#predictor.print_modsel_params()
# build parameter tree to select regularization parameter
param_tree_root = create_param_tree()
# model selection instance
model_selection = GridSearchModelSelection(cross_validation,
param_tree_root)
# perform model selection with selected methods
#print "performing model selection of"
#print "parameter tree:"
#param_tree_root.print_tree()
#print "starting model selection"
# print the current parameter combination, if no parameter nothing is printed
print_state = False
best_parameters = model_selection.select_model(print_state)
# print best parameters
#print "best parameters:"
#best_parameters.print_tree()
# apply them and print result
best_parameters.apply_to_machine(predictor)
result = cross_validation.evaluate()
# train ordinary LSR
if use_ridge:
lsr = LinearRidgeRegression(0.01, RealFeatures(X.T), Labels(y))
lsr.train()
else:
lsr = LeastSquaresRegression()
lsr.set_labels(RegressionLabels(y))
lsr.train(RealFeatures(X.T))
# gather LASSO path
path = np.zeros((p, LeastAngleRegression.get_path_size()))
for i in xrange(path.shape[1]):
path[:, i] = LeastAngleRegression.get_w(i)
evaluator = MeanSquaredError()
# apply on training data
mse_train = np.zeros(LeastAngleRegression.get_path_size())
for i in xrange(mse_train.shape[0]):
LeastAngleRegression.switch_w(i)
ypred = LeastAngleRegression.apply(RealFeatures(X.T))
mse_train[i] = evaluator.evaluate(ypred, RegressionLabels(y))
ypred = lsr.apply(RealFeatures(X.T))
mse_train_lsr = evaluator.evaluate(ypred, RegressionLabels(y))
# apply on test data
mse_test = np.zeros(LeastAngleRegression.get_path_size())
for i in xrange(mse_test.shape[0]):
LeastAngleRegression.switch_w(i)
ypred = LeastAngleRegression.apply(RealFeatures(Xtest.T))
def modelselection_grid_search_libsvr_modular (fm_train=traindat,fm_test=testdat,label_train=label_traindat,\
width=2.1,C=1,epsilon=1e-5,tube_epsilon=1e-2):
from modshogun import CrossValidation, CrossValidationResult
from modshogun import MeanSquaredError
from modshogun import CrossValidationSplitting
from modshogun import RegressionLabels
from modshogun import RealFeatures
from modshogun import GaussianKernel
from modshogun import LibSVR
from modshogun import GridSearchModelSelection
from modshogun import ModelSelectionParameters, R_EXP
from modshogun import ParameterCombination
# training data
features_train = RealFeatures(traindat)
labels = RegressionLabels(label_traindat)
# kernel
kernel = GaussianKernel(features_train, features_train, width)
# print all parameter available for modelselection
# Dont worry if yours is not included but, write to the mailing list
#kernel.print_modsel_params()
labels = RegressionLabels(label_train)
# predictor
predictor = LibSVR(C, tube_epsilon, kernel, labels)
predictor.set_epsilon(epsilon)
# splitting strategy for 5 fold cross-validation (for classification its better
# to use "StratifiedCrossValidation", but the standard
# "StratifiedCrossValidationSplitting" is also available
splitting_strategy = CrossValidationSplitting(labels, 5)
# evaluation method
evaluation_criterium = MeanSquaredError()
# cross-validation instance
cross_validation = CrossValidation(predictor, features_train, labels,
splitting_strategy,
evaluation_criterium)
# (optional) repeat x-val (set larger to get better estimates, at least two
# for confidence intervals)
cross_validation.set_num_runs(2)
# (optional) request 95% confidence intervals for results (not actually
# needed for this toy example)
cross_validation.set_conf_int_alpha(0.05)
# print all parameter available for modelselection
# Dont worry if yours is not included but, write to the mailing list
#predictor.print_modsel_params()
# build parameter tree to select C1 and C2
param_tree_root = ModelSelectionParameters()
c1 = ModelSelectionParameters("C1")
param_tree_root.append_child(c1)
c1.build_values(-1.0, 0.0, R_EXP)
c2 = ModelSelectionParameters("C2")
param_tree_root.append_child(c2)
c2.build_values(-1.0, 0.0, R_EXP)
# model selection instance
model_selection = GridSearchModelSelection(cross_validation,
param_tree_root)
# perform model selection with selected methods
#print "performing model selection of"
#print "parameter tree"
#param_tree_root.print_tree()
#print "starting model selection"
# print the current parameter combination, if no parameter nothing is printed
print_state = False
# lock data before since model selection will not change the kernel matrix
# (use with care) This avoids that the kernel matrix is recomputed in every
# iteration of the model search
predictor.data_lock(labels, features_train)
best_parameters = model_selection.select_model(print_state)
# print best parameters
#print "best parameters:"
#best_parameters.print_tree()
# apply them and print result
best_parameters.apply_to_machine(predictor)
result = cross_validation.evaluate()
# train ordinary LSR
if use_ridge:
lsr = LinearRidgeRegression(0.01, RealFeatures(X.T), Labels(y))
lsr.train()
else:
lsr = LeastSquaresRegression()
lsr.set_labels(RegressionLabels(y))
lsr.train(RealFeatures(X.T))
# gather LASSO path
path = np.zeros((p, LeastAngleRegression.get_path_size()))
for i in xrange(path.shape[1]):
path[:, i] = LeastAngleRegression.get_w(i)
evaluator = MeanSquaredError()
# apply on training data
mse_train = np.zeros(LeastAngleRegression.get_path_size())
for i in xrange(mse_train.shape[0]):
LeastAngleRegression.switch_w(i)
ypred = LeastAngleRegression.apply(RealFeatures(X.T))
mse_train[i] = evaluator.evaluate(ypred, RegressionLabels(y))
ypred = lsr.apply(RealFeatures(X.T))
mse_train_lsr = evaluator.evaluate(ypred, RegressionLabels(y))
# apply on test data
mse_test = np.zeros(LeastAngleRegression.get_path_size())
for i in xrange(mse_test.shape[0]):
LeastAngleRegression.switch_w(i)
ypred = LeastAngleRegression.apply(RealFeatures(Xtest.T))
